{"id":"https://openalex.org/W4401163927","doi":"https://doi.org/10.1109/eit60633.2024.10609911","title":"Malware Dataset Availability &amp; Inherent Bias Study","display_name":"Malware Dataset Availability &amp; Inherent Bias Study","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4401163927","doi":"https://doi.org/10.1109/eit60633.2024.10609911"},"language":"en","primary_location":{"id":"doi:10.1109/eit60633.2024.10609911","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/eit60633.2024.10609911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Electro Information Technology (eIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078608243","display_name":"W. F. K. Thompson","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren Thompson","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106109852","display_name":"Talal Elammas","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Talal Elammas","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106063609","display_name":"Mahesh Kalappattil","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahesh Kalappattil","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113140973","display_name":"Anthony Rizi","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Rizi","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113313170","display_name":"Greg Sunderland","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Sunderland","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106160319","display_name":"Leonardo Baldizon","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonardo Baldizon","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007506024","display_name":"Frank S Posluszny","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Posluszny","raw_affiliation_strings":["The MITRE Corporation,McLean,VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation,McLean,VA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003067300","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0002-2719-1017"},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dakota State University,The Beacom College of Computer and Cyber Sciences,Madison,SD,57042","institution_ids":["https://openalex.org/I125467818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3057,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50808204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"abs/2111.15205","issue":null,"first_page":"202","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.9513000249862671,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.8029302358627319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7249971032142639},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.391751766204834},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36248907446861267},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3526275157928467}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8029302358627319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249971032142639},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.391751766204834},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36248907446861267},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3526275157928467}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/eit60633.2024.10609911","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/eit60633.2024.10609911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Electro Information Technology (eIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W94487276","https://openalex.org/W2742353928","https://openalex.org/W2770258819","https://openalex.org/W2784030825","https://openalex.org/W2914560477","https://openalex.org/W3086227660","https://openalex.org/W3118612008","https://openalex.org/W3214916885","https://openalex.org/W3217279074","https://openalex.org/W4313495867","https://openalex.org/W4328028524","https://openalex.org/W6753153400"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2097492617","https://openalex.org/W2753240997","https://openalex.org/W1764168690","https://openalex.org/W2537959205","https://openalex.org/W2740895074","https://openalex.org/W2772446090","https://openalex.org/W4284893819","https://openalex.org/W2249809453"],"abstract_inverted_index":{"Research":[0],"in":[1],"malware":[2,17,27,38,73,130],"analysis":[3],"faces":[4],"significant":[5],"challenges,":[6],"especially":[7],"when":[8],"dealing":[9],"with":[10,112],"datasets.":[11],"The":[12,75],"limitations":[13],"imposed":[14],"by":[15],"outdated":[16],"samples":[18],"and":[19,48,81,99,126,142],"inaccurate":[20],"tagging":[21],"restrict":[22],"the":[23,92,103],"utility":[24],"of":[25,37,45,61,88,94],"specific":[26],"datasets":[28,55,63,104],"for":[29,66,72,140],"research.":[30],"This":[31],"paper":[32],"undertakes":[33],"a":[34,86],"comprehensive":[35],"examination":[36],"datasets,":[39,84],"aiming":[40],"to":[41,156],"enhance":[42],"our":[43,58],"understanding":[44],"cyber":[46],"threats":[47],"strengthen":[49],"cybersecurity":[50,143],"strategies.":[51],"We":[52],"identified":[53],"27":[54],"that":[56,152,158],"satisfied":[57],"criteria.":[59],"Three":[60],"those":[62,83],"were":[64],"selected":[65],"further":[67],"enumeration":[68],"using":[69],"VirusTotal\u2019s":[70],"API":[71],"analysis.":[74],"method":[76],"presented":[77],"here":[78],"systematically":[79],"evaluates":[80],"categorizes":[82],"considering":[85],"number":[87],"factors":[89],"such":[90],"as":[91],"availability":[93],"raw":[95],"samples,":[96],"temporal":[97,113],"relevancy,":[98],"sample":[100],"quantity.":[101],"Examining":[102],"through":[105],"quantitative":[106],"methods":[107],"exposes":[108],"nuanced":[109],"biases":[110],"associated":[111],"factors,":[114],"file":[115],"types":[116],"(e.g.,":[117,122,132],".exe,":[118],".elf),":[119],"hardware":[120],"architectures":[121],"ARM,":[123],"x86,":[124],"x64),":[125],"distributions":[127],"across":[128],"various":[129],"categories":[131],"trojan,":[133],"droppers,":[134],"spam).":[135],"These":[136],"insights":[137],"are":[138],"crucial":[139],"researchers":[141],"professionals":[144],"who":[145],"intend":[146],"on":[147],"employing":[148],"machine":[149],"learning":[150],"models":[151],"may":[153,159],"be":[154,160],"susceptible":[155],"bias":[157],"present.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
